| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.5, | |
| "eval_steps": 20, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.588, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.5849277377128601, | |
| "eval_runtime": 13.5251, | |
| "eval_samples_per_second": 1.848, | |
| "eval_steps_per_second": 0.296, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5065, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.5613898634910583, | |
| "eval_runtime": 13.3646, | |
| "eval_samples_per_second": 1.871, | |
| "eval_steps_per_second": 0.299, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4523, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.9986331433523156e-05, | |
| "loss": 0.5692, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.5513718724250793, | |
| "eval_runtime": 13.3937, | |
| "eval_samples_per_second": 1.867, | |
| "eval_steps_per_second": 0.299, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.994534068046937e-05, | |
| "loss": 0.5257, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.9877072563625285e-05, | |
| "loss": 0.4937, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.5424299836158752, | |
| "eval_runtime": 13.4443, | |
| "eval_samples_per_second": 1.86, | |
| "eval_steps_per_second": 0.298, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.978160173317438e-05, | |
| "loss": 0.5617, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.965903258506806e-05, | |
| "loss": 0.3592, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5260083675384521, | |
| "eval_runtime": 13.4207, | |
| "eval_samples_per_second": 1.863, | |
| "eval_steps_per_second": 0.298, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.9509499146870236e-05, | |
| "loss": 0.4586, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.933316493120015e-05, | |
| "loss": 0.3724, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.5247484445571899, | |
| "eval_runtime": 13.4092, | |
| "eval_samples_per_second": 1.864, | |
| "eval_steps_per_second": 0.298, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.913022275693372e-05, | |
| "loss": 0.3205, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.8900894538358944e-05, | |
| "loss": 0.4962, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.5248944163322449, | |
| "eval_runtime": 13.4511, | |
| "eval_samples_per_second": 1.859, | |
| "eval_steps_per_second": 0.297, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.864543104251587e-05, | |
| "loss": 0.3324, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.8364111614986527e-05, | |
| "loss": 0.4781, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.5312905311584473, | |
| "eval_runtime": 13.4112, | |
| "eval_samples_per_second": 1.864, | |
| "eval_steps_per_second": 0.298, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.805724387443462e-05, | |
| "loss": 0.3429, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.7725163376229064e-05, | |
| "loss": 0.3504, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.5292657017707825, | |
| "eval_runtime": 13.3837, | |
| "eval_samples_per_second": 1.868, | |
| "eval_steps_per_second": 0.299, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.736823324551909e-05, | |
| "loss": 0.4843, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.698684378016222e-05, | |
| "loss": 0.2449, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5281097292900085, | |
| "eval_runtime": 13.438, | |
| "eval_samples_per_second": 1.86, | |
| "eval_steps_per_second": 0.298, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.6581412023939354e-05, | |
| "loss": 0.3535, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 4.6152381310523387e-05, | |
| "loss": 0.2264, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.5974144339561462, | |
| "eval_runtime": 13.4417, | |
| "eval_samples_per_second": 1.86, | |
| "eval_steps_per_second": 0.298, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.5700220778700504e-05, | |
| "loss": 0.2303, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.3395, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.5777361989021301, | |
| "eval_runtime": 13.414, | |
| "eval_samples_per_second": 1.864, | |
| "eval_steps_per_second": 0.298, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.4728512734909844e-05, | |
| "loss": 0.1651, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.421002777142148e-05, | |
| "loss": 0.3093, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.5854852199554443, | |
| "eval_runtime": 13.4001, | |
| "eval_samples_per_second": 1.866, | |
| "eval_steps_per_second": 0.299, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.367053692460385e-05, | |
| "loss": 0.2512, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.311063011977723e-05, | |
| "loss": 0.2054, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.5999884605407715, | |
| "eval_runtime": 13.4618, | |
| "eval_samples_per_second": 1.857, | |
| "eval_steps_per_second": 0.297, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.2530919606812216e-05, | |
| "loss": 0.3547, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.193203929064353e-05, | |
| "loss": 0.1739, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5840221047401428, | |
| "eval_runtime": 13.4097, | |
| "eval_samples_per_second": 1.864, | |
| "eval_steps_per_second": 0.298, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.131464403810422e-05, | |
| "loss": 0.1787, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.067940896183843e-05, | |
| "loss": 0.1165, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.6706953644752502, | |
| "eval_runtime": 13.4189, | |
| "eval_samples_per_second": 1.863, | |
| "eval_steps_per_second": 0.298, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 4.002702868207563e-05, | |
| "loss": 0.1477, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.935821656707359e-05, | |
| "loss": 0.2011, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 0.6934244632720947, | |
| "eval_runtime": 13.403, | |
| "eval_samples_per_second": 1.865, | |
| "eval_steps_per_second": 0.298, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 3.867370395306068e-05, | |
| "loss": 0.1066, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1000, | |
| "num_train_epochs": 10, | |
| "save_steps": 50, | |
| "total_flos": 4.924285778959565e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |